> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chainlit.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Step

LLM powered Assistants take multiple steps to process a user's request, forming a chain of thought.
Unlike a [Message](concepts/message), a Step has a type, an input/output and a start/end.

Depending on the `config.ui.cot` setting, the full chain of thought can be displayed in full, hidden or only the tool calls.

## A Simple Tool Calling Example

Lets take a simple example of a Chain of Thought that takes a user's message, process it and sends a response.

```py theme={null}
import chainlit as cl


@cl.step(type="tool")
async def tool():
    # Simulate a running task
    await cl.sleep(2)

    return "Response from the tool!"


@cl.on_message
async def main(message: cl.Message):
    # Call the tool
    tool_res = await tool()

    # Send the final answer.
    await cl.Message(content="This is the final answer").send()
```

<Frame caption="Output of the code above">
  <img src="https://mintcdn.com/chainlit-43/bY2N4qUEa_bGPLfY/images/step.png?fit=max&auto=format&n=bY2N4qUEa_bGPLfY&q=85&s=9239955d2ac9dc61a4b44aa760701f3c" width="2782" height="900" data-path="images/step.png" />
</Frame>

## Step API

There are two ways to create steps, either by using the the `@cl.step` decorator or by using the `cl.Step` class.

<CardGroup cols={2}>
  <Card title="@cl.step" icon="at" color="#F80061" href="/api-reference/step-decorator">
    Easier to use but requires to split your step logic in a function.
  </Card>

  <Card title="with cl.Step():" icon="code" color="#F80061" href="/api-reference/step-class">
    More verbose but usable in any context as a Python Context Manager.
  </Card>
</CardGroup>